© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20290
    Prev
    Next
    INDEX
    Explanations

    negative consequences or risks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç«ŀ
    -0.06
    übers
    -0.05
     NET
    -0.05
    æĹł
    -0.05
     ‘
    -0.05
    chet
    -0.05
    NET
    -0.05
    éĺ³æĺ¥
    -0.05
    ç½ij
    -0.05
     edge
    -0.05
    POSITIVE LOGITS
    çıij
    0.06
    -hide
    0.06
    iage
    0.06
    è¿Ľä¸ĢæŃ¥åĬłå¤§
    0.06
    ney
    0.06
    è¿Ľä¸ĢæŃ¥çļĦ
    0.06
    åĨįåĪ©çĶ¨
    0.06
    å°±æѤ
    0.06
    oto
    0.05
    faits
    0.05
    Activations Density 0.027%

    No Known Activations